The invention provides an attack identification method based on a K nearest neighbor algorithm, which comprises the following steps: if a normal database and an abnormal database after being attackedby a network are established, taking all classifications as reference sample groups to obtain a reference database; extracting real-time data from a message, and classifying the real-time data and thereference database through a K nearest neighbor algorithm to obtain the category of the data; sending an attack alarm and generating a log record for storage when the real-time data includes the dataclassified into a network attack category, and intercepting the data classified into the network attack category; meanwhile, forwarding the data classified into a normal category in the real-time data; and forwarding the real-time data when the real-time data does not include the data classified into the network attack category. The invention further provides a charging device. Compared with theprior art, the information safety and the operation reliability of the charging device are ensured, and the safety of a power grid is ensured.

    本发明提供了一种基于K最近邻算法攻击识别方法,包括如建立正常数据库以及被网络攻击后的异常数据库,将所有分类分别作为参考样本组得到参考数据库;提取报文中的实时的数据后将实时的数据与参考数据库通过K最近邻算法对实时的数据进行分类,得出数据的所述分类;当实时的数据中存在数据归入的分类为网络攻击类别时,发出攻击报警和生成日志记录进行保存,同时对归入网络攻击类的数据进行拦截;同时对实时数据中归入正常类的数据进行转发;当实时数据中不存在数据归入的分类为网络攻击类别时,则将实时数据进行转发。本发明还提供了一种充电装置。与现有技术相比,保证充电装置的信息安全性以及运行可靠性,保障电网的安全。


    Access

    Download


    Export, share and cite



    Title :

    Attack identification method based on K nearest neighbor algorithm and charging device


    Additional title:

    基于K最近邻算法攻击识别方法及充电装置


    Contributors:
    LIN ZIZHAO (author) / XU CHENGBIN (author) / HUANG ZHIWEI (author) / HUANG FUQUAN (author) / CHEN RUI (author) / ZU LIANXING (author) / DING KAI (author) / ZHU XIAOFAN (author) / CHEN YUANSHENG (author) / ZHAN JIEWEN (author)

    Publication date :

    2020-04-17


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen



    Fast nearest-neighbor search algorithm [2669-11]

    Darwish, A. M. / SPIE | British Library Conference Proceedings | 1996


    A Road Hotspots Identification Method Based on Natural Nearest Neighbor Clustering

    Han, Qingwen / Zhu, Yingxiang / Zeng, Lingqiu et al. | IEEE | 2015


    3DNN: 3D Nearest Neighbor

    Satkin, S. / Rashid, M. / Lin, J. et al. | British Library Online Contents | 2015



    Accelerated image classification algorithm based on naive Bayes K-nearest neighbor

    Zhang, Xu / Jiang, Jianguo / Hong, Richang et al. | British Library Online Contents | 2015